You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by sr...@apache.org on 2018/07/31 20:23:15 UTC
spark git commit: [SPARK-24973][PYTHON] Add numIter to Python
ClusteringSummary
Repository: spark
Updated Branches:
refs/heads/master e82784d13 -> 42dfe4f15
[SPARK-24973][PYTHON] Add numIter to Python ClusteringSummary
## What changes were proposed in this pull request?
Add numIter to Python version of ClusteringSummary
## How was this patch tested?
Modified existing UT test_multiclass_logistic_regression_summary
Author: Huaxin Gao <hu...@us.ibm.com>
Closes #21925 from huaxingao/spark-24973.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/42dfe4f1
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/42dfe4f1
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/42dfe4f1
Branch: refs/heads/master
Commit: 42dfe4f1593767eae355e27bf969339f4ab03f56
Parents: e82784d
Author: Huaxin Gao <hu...@us.ibm.com>
Authored: Tue Jul 31 15:23:11 2018 -0500
Committer: Sean Owen <sr...@gmail.com>
Committed: Tue Jul 31 15:23:11 2018 -0500
----------------------------------------------------------------------
python/pyspark/ml/clustering.py | 8 ++++++++
python/pyspark/ml/tests.py | 3 +++
2 files changed, 11 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/42dfe4f1/python/pyspark/ml/clustering.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/clustering.py b/python/pyspark/ml/clustering.py
index 8a58d83..ef9822d 100644
--- a/python/pyspark/ml/clustering.py
+++ b/python/pyspark/ml/clustering.py
@@ -88,6 +88,14 @@ class ClusteringSummary(JavaWrapper):
"""
return self._call_java("clusterSizes")
+ @property
+ @since("2.4.0")
+ def numIter(self):
+ """
+ Number of iterations.
+ """
+ return self._call_java("numIter")
+
class GaussianMixtureModel(JavaModel, JavaMLWritable, JavaMLReadable):
"""
http://git-wip-us.apache.org/repos/asf/spark/blob/42dfe4f1/python/pyspark/ml/tests.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py
index bc78213..3d8883b 100755
--- a/python/pyspark/ml/tests.py
+++ b/python/pyspark/ml/tests.py
@@ -1888,6 +1888,7 @@ class TrainingSummaryTest(SparkSessionTestCase):
self.assertTrue(isinstance(s.cluster, DataFrame))
self.assertEqual(len(s.clusterSizes), 2)
self.assertEqual(s.k, 2)
+ self.assertEqual(s.numIter, 3)
def test_bisecting_kmeans_summary(self):
data = [(Vectors.dense(1.0),), (Vectors.dense(5.0),), (Vectors.dense(10.0),),
@@ -1903,6 +1904,7 @@ class TrainingSummaryTest(SparkSessionTestCase):
self.assertTrue(isinstance(s.cluster, DataFrame))
self.assertEqual(len(s.clusterSizes), 2)
self.assertEqual(s.k, 2)
+ self.assertEqual(s.numIter, 20)
def test_kmeans_summary(self):
data = [(Vectors.dense([0.0, 0.0]),), (Vectors.dense([1.0, 1.0]),),
@@ -1918,6 +1920,7 @@ class TrainingSummaryTest(SparkSessionTestCase):
self.assertTrue(isinstance(s.cluster, DataFrame))
self.assertEqual(len(s.clusterSizes), 2)
self.assertEqual(s.k, 2)
+ self.assertEqual(s.numIter, 1)
class KMeansTests(SparkSessionTestCase):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org